Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to accidents

    oai_token-act-pair · gpt-3.5-turbo

    references to accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.83
    ongyang
    -0.81
    uggish
    -0.78
    intendo
    -0.77
    orthy
    -0.73
    acha
    -0.73
    reens
    -0.72
    Pr
    -0.72
    ills
    -0.71
    aida
    -0.69
    POSITIVE LOGITS
     accident
    1.17
     accidents
    0.89
     mish
    0.85
     crash
    0.82
     bystand
    0.76
     wreck
    0.74
     crashes
    0.72
     Franch
    0.70
     collision
    0.70
     Odyssey
    0.68
    Act Density 0.010%

    No Known Activations